Views
No views yet
| Run locally | Pool multiple machines | OpenAI-compatible | Package variant |
|---|---|---|---|
| Private inference on your hardware | Split layers across peers | Serve /v1/chat/completions locally | UD-Q4_K_XL layer package |
| Property | Value |
|---|---|
| Source model | unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF |
| Model id | unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF:UD-Q4_K_XL |
| Family | Qwen3 |
| Parameter scale | 80B-A3B |
| Quantization | UD-Q4_K_XL |
| Layer count | 48 |
| Activation width | 2048 |
| Package size | 43.2 GB |
| Source file | Qwen3-Next-80B-A3B-Instruct-UD-Q4_K_XL.gguf |
| Package repo | meshllm/Qwen3-Next-80B-A3B-Instruct-UD-Q4_K_XL-layers |
1# Run this on each machine that should contribute memory/compute.
2mesh-llm serve --model "meshllm/Qwen3-Next-80B-A3B-Instruct-UD-Q4_K_XL-layers" --split1# Check the mesh and discover the OpenAI-compatible model name.
2curl -s http://localhost:3131/api/status
3curl -s http://localhost:3131/v1/models1# Send an OpenAI-compatible chat request.
2curl -s http://localhost:3131/v1/chat/completions \
3 -H "Content-Type: application/json" \
4 -d '{
5 "model": "unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF:UD-Q4_K_XL",
6 "messages": [{"role": "user", "content": "Write a tiny hello-world function in Rust."}],
7 "max_tokens": 128
8 }'| Property | Value |
|---|---|
| Format | layer-package |
| Canonical source ref | unsloth/Qwen3-Next-80B-A3B-Instruct-GGUF@main/Qwen3-Next-80B-A3B-Instruct-UD-Q4_K_XL.gguf |
| Source revision | main |
| Source SHA-256 | 49e554f954afbfc9f627b8be236adf16c1e51d8e5ecaa0e65ac8ede4e2c41a56 |
| Skippy ABI | 0.1.24 |
| Package manifest SHA-256 | bdb6ac8baa31171143922dc8c2ca542c91e0eb405089e4602277a76953e4800a |
| Artifact | Path | Contents | SHA-256 |
|---|---|---|---|
| Manifest | model-package.json | Package schema, source identity, checksums | bdb6ac8baa31171143922dc8c2ca542c91e0eb405089e4602277a76953e4800a |
| Metadata | shared/metadata.gguf | 0 tensors, 5.7 MB | 2fddd750d1a4b1de7985cd6170078d62b936aa4d921a45fab07bd3221ed47cd8 |
| Embeddings | shared/embeddings.gguf | 1 tensors, 172.6 MB | b44fb62424936996f4de935d421e1270df0a6eaa7fba5e1a39f426e8682548a8 |
| Output head | shared/output.gguf | 2 tensors, 249.1 MB | b2c866f0a8feb468ae62f20559bc2ecf79dd28d8946680044ebc662bfbcd6e3a |
| Transformer layers | layers/layer-*.gguf | 48 layer artifacts, 840 tensors, 42.8 GB | see model-package.json |
mesh-llm ref main.
Each artifact is checksummed as it is written, uploaded to this repository, and removed from the job workspace before the next artifact is produced.skippy-model-package write-package "/source/Qwen3-Next-80B-A3B-Instruct-UD-Q4_K_XL.gguf" --out-dir "/tmp/meshllm-layer-job-meshllm_Qwen3-Next-80B-A3B-Instruct-UD-Q4_K_XL-layers-199/package"